TY - GEN
T1 - Redundancy in speech signals and robustness of automatic speech recognition
AU - Yousafzai, Jibran
AU - Cvetković, Zoran
AU - Ager, Matthew
AU - Sollich, Peter
PY - 2012
Y1 - 2012
N2 - Automatic speech recognition (ASR) systems are yet to achieve the level of robustness inherent to speech recognition by the human auditory system. The primary goal of this paper is to argue that exploiting the redundancy in speech signals could be the key to solving the problem of the lack of robustness. This view is supported by our recent results on phoneme classification and recognition in the presence of noise which are surveyed in this paper.
AB - Automatic speech recognition (ASR) systems are yet to achieve the level of robustness inherent to speech recognition by the human auditory system. The primary goal of this paper is to argue that exploiting the redundancy in speech signals could be the key to solving the problem of the lack of robustness. This view is supported by our recent results on phoneme classification and recognition in the presence of noise which are surveyed in this paper.
UR - http://www.scopus.com/inward/record.url?scp=84870612165&partnerID=8YFLogxK
U2 - 10.1109/RED.2012.6338416
DO - 10.1109/RED.2012.6338416
M3 - Conference contribution
AN - SCOPUS:84870612165
SN - 9781467301701
T3 - Proceedings - 2012 13th International Symposium on Problems of Redundancy in Information and Control Systems, RED 2012
SP - 93
EP - 98
BT - Proceedings - 2012 13th International Symposium on Problems of Redundancy in Information and Control Systems, RED 2012
T2 - 2012 13th International Symposium on Problems of Redundancy in Information and Control Systems, RED 2012
Y2 - 5 September 2012 through 10 September 2012
ER -